license: apache-2.0
tags:
- 图像分类
- 训练生成
metrics:
- 准确率
model-index:
- name: exper_batch_16_e8
results: []
exper_batch_16_e8
本模型是基于google/vit-base-patch16-224-in21k在sudo-s/herbier_mesuem1数据集上微调的版本。在评估集上取得了以下结果：
模型描述
（需补充详细信息）
适用范围与限制
（需补充详细信息）
训练与评估数据
（需补充详细信息）
训练流程
训练超参数
训练过程中使用了以下超参数：
- 学习率：0.0002
- 训练批次大小：16
- 评估批次大小：8
- 随机种子：42
- 优化器：Adam（beta系数0.9/0.999，epsilon=1e-08）
- 学习率调度器类型：线性
- 训练轮次：8
- 混合精度训练：Apex（优化级别O1）
训练结果
| 训练损失 |
轮次 |
步数 |
验证损失 |
准确率 |
| 3.8115 |
0.16 |
100 |
3.7948 |
18.62% |
| 3.1194 |
0.31 |
200 |
3.0120 |
32.81% |
| 2.3703 |
0.47 |
300 |
2.4791 |
44.26% |
| 2.07 |
0.63 |
400 |
2.1720 |
50.00% |
| 1.6847 |
0.78 |
500 |
1.7291 |
59.56% |
| 1.3821 |
0.94 |
600 |
1.4777 |
62.99% |
| 0.9498 |
1.1 |
700 |
1.2935 |
66.81% |
| 0.8741 |
1.25 |
800 |
1.1353 |
70.51% |
| 0.8875 |
1.41 |
900 |
0.9951 |
74.48% |
| 0.7233 |
1.56 |
1000 |
0.9265 |
74.87% |
| 0.6696 |
1.72 |
1100 |
0.8660 |
76.25% |
| 0.7364 |
1.88 |
1200 |
0.8710 |
75.79% |
| 0.3933 |
2.03 |
1300 |
0.7162 |
80.38% |
| 0.3443 |
2.19 |
1400 |
0.6305 |
83.00% |
| 0.3376 |
2.35 |
1500 |
0.6273 |
83.15% |
| 0.3071 |
2.5 |
1600 |
0.5988 |
83.19% |
| 0.2863 |
2.66 |
1700 |
0.6731 |
81.53% |
| 0.3017 |
2.82 |
1800 |
0.6042 |
83.15% |
| 0.2382 |
2.97 |
1900 |
0.5118 |
87.12% |
| 0.1578 |
3.13 |
2000 |
0.4917 |
87.36% |
| 0.1794 |
3.29 |
2100 |
0.5302 |
86.31% |
| 0.1093 |
3.44 |
2200 |
0.5035 |
86.35% |
| 0.1076 |
3.6 |
2300 |
0.5186 |
86.74% |
| 0.1219 |
3.76 |
2400 |
0.4723 |
88.01% |
| 0.1017 |
3.91 |
2500 |
0.5132 |
87.12% |
| 0.0351 |
4.07 |
2600 |
0.4709 |
87.28% |
| 0.0295 |
4.23 |
2700 |
0.4674 |
88.24% |
| 0.0416 |
4.38 |
2800 |
0.4836 |
88.05% |
| 0.0386 |
4.54 |
2900 |
0.4663 |
88.28% |
| 0.0392 |
4.69 |
3000 |
0.4003 |
89.90% |
| 0.0383 |
4.85 |
3100 |
0.4187 |
89.48% |
| 0.0624 |
5.01 |
3200 |
0.4460 |
88.74% |
| 0.0188 |
5.16 |
3300 |
0.4169 |
90.29% |
| 0.0174 |
5.32 |
3400 |
0.4098 |
89.51% |
| 0.0257 |
5.48 |
3500 |
0.4289 |
89.51% |
| 0.0123 |
5.63 |
3600 |
0.4295 |
90.29% |
| 0.0052 |
5.79 |
3700 |
0.4395 |
89.94% |
| 0.0081 |
5.95 |
3800 |
0.4217 |
90.82% |
| 0.0032 |
6.1 |
3900 |
0.4216 |
90.56% |
| 0.0033 |
6.26 |
4000 |
0.4113 |
90.82% |
| 0.0024 |
6.42 |
4100 |
0.4060 |
91.02% |
| 0.0022 |
6.57 |
4200 |
0.4067 |
90.90% |
| 0.0031 |
6.73 |
4300 |
0.4005 |
91.13% |
| 0.0021 |
6.89 |
4400 |
0.4008 |
91.29% |
| 0.0021 |
7.04 |
4500 |
0.3967 |
91.13% |
| 0.0043 |
7.2 |
4600 |
0.3960 |
91.21% |
| 0.0022 |
7.36 |
4700 |
0.3962 |
91.25% |
| 0.0021 |
7.51 |
4800 |
0.3992 |
91.21% |
| 0.002 |
7.67 |
4900 |
0.3951 |
91.29% |
| 0.0023 |
7.82 |
5000 |
0.3952 |
91.25% |
| 0.0021 |
7.98 |
5100 |
0.3952 |
91.29% |
框架版本
- Transformers 4.19.4
- Pytorch 1.5.1
- Datasets 2.3.2
- Tokenizers 0.12.1
Transformers%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20none;%20}%20.st1%20{%20fill:%20%235ce6cf;%20}%20.st2%20{%20fill:%20%230080ff;%20}%20.st3%20{%20clip-path:%20url(%23clippath);%20}%20%3c/style%3e%3cclipPath%20id='clippath'%3e%3crect%20class='st0'%20y='0'%20width='120'%20height='32'/%3e%3c/clipPath%3e%3c/defs%3e%3cg%20class='st3'%3e%3cg%3e%3cpath%20class='st1'%20d='M22.4,32H3.2c-1,0-2-.5-2.6-1.4-.6-.9-.7-2-.4-2.9L9.8,2.1C10.3.8,11.5,0,12.8,0s2.5.8,3,2.1l9.6,25.6c.4,1,.2,2.1-.4,2.9-.6.9-1.6,1.4-2.6,1.4ZM7.8,25.6h10l-5-13.3-5,13.3Z'/%3e%3cpath%20class='st2'%20d='M33.6,32c-1.3,0-2.5-.8-3-2.1L21,4.3c-.6-1.7.2-3.5,1.9-4.1,1.7-.6,3.5.2,4.1,1.9l9.6,25.6c.6,1.7-.2,3.5-1.9,4.1-.4.1-.8.2-1.1.2h0Z'/%3e%3cpath%20d='M71.8,9.1h-6.9v4.6h6.9c2.5,0,4.6,2,4.6,4.6h-6.9c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h2.3c1.7,0,3.2-.4,4.6-1.2v1.2h4.6v-13.7c0-5-4.1-9.1-9.1-9.1h0ZM71.8,27.4h-2.3c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h6.9c0,2.5-2,4.6-4.6,4.6h0Z'/%3e%3cpath%20d='M52.3,9.1h-4.6V0h-4.6V32h9.1c5,0,9.1-4.1,9.1-9.1v-4.6c0-5.1-4.1-9.1-9.1-9.1h0ZM56.9,22.9c0,2.5-2,4.6-4.6,4.6h-4.6v-13.7h4.6c2.5,0,4.6,2,4.6,4.6v4.6h0Z'/%3e%3cpath%20d='M110.9,13.7h9.1v-4.6h-9.1c-5.1,0-9.1,4.1-9.1,9.1v4.6c0,5.1,4.1,9.1,9.1,9.1h9.1v-4.6h-9.1c-2.5,0-4.6-2-4.6-4.6h13.7v-4.6h-13.7c0-2.5,2-4.6,4.6-4.6h0Z'/%3e%3cpath%20d='M93.6,18.3h-4.6c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h10.3v-4.6h-10.3c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h4.6c1.3,0,2.3,1,2.3,2.3s-1,2.3-2.3,2.3h-10.3v4.6h10.3c3.8,0,6.9-3.1,6.9-6.9s-3.1-6.9-6.9-6.9Z'/%3e%3c/g%3e%3c/g%3e%3c/svg%3e)